Hello Remi, Am 17.01.2012 um 20:21 schrieb Rémi Coulom:
> > On 17 janv. 2012, at 11:05, Ingo Althöfer wrote: > >> Hello Remi, >> >> thanks a lot for your nice service. >> Hopefully, this feature will flow also in forthcoming >> commercial versions of CrazyStone. > > Hi Ingo, > > Since many people seem so interested, we may try to include it in the next > version. Yeah, this analysis Tool is quite exciting. I hope you develop this further. But in order to avoid confusing weaker players, it would be good if you calculate the standard deviation of P(B wins) and only call a move "recommended" if its more than one SD away from the played move. Otherwise weaker players might get the impression the program evaluated the played move as weaker, when in fact it hat just fewer playouts to make a accurate estimation. Best regards David O. _______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
